Method and device for acquiring region of interest of medical image, medium and equipment
Through coordinate conversion and offset processing technology, the complex problem of oblique medical image labeling is solved, and the method of accurately determining the three-dimensional area of interest on two-dimensional images is realized, ensuring the fit and accuracy of the area.
Patent Information
- Application Number
- CN202410897154.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-04
- Publication Date
- 2024-11-05
AI Technical Summary
The prior art is complex in labeling on oblique medical images, and mainstream software has failed to successfully realize the labeling of three-dimensional areas of interest, especially when multi-layer medical images are superimposed into three-dimensional bodies.
The region of interest of medical images is obtained by converting the first vertex coordinates in the first coordinate system into the second vertex coordinates in the second coordinate system, determining the coordinate range, and excluding the coordinate range. The method includes image facet processing, coordinate conversion and offset processing to ensure that the area of interest is accurately matched with the user's intentions.
In the case of any oblique medical image, the three-dimensional area of interest can be determined from the two-dimensional image according to the user's intention, ensuring the complete fit and accuracy of the area, and providing a kind of area of interest for the oblique medical image An efficient and reliable implementation method.
Smart Images

Figure CN118898577A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure belongs to the field of image processing technology, and in particular, relates to a method for acquiring a region of interest of a medical image, a device for acquiring a region of interest of a medical image, a computer-readable storage medium, and an electronic device. Background Art
[0002] Medical image MPR (Multi-planar Reconstruction) is based on the conversion of multi-layer medical images into two-dimensional images at different perspectives, which are often divided into coronal plane, sagittal plane and axial plane. With the advancement of hardware technology, it is now possible to display the coronal plane, sagittal plane and axial plane in an oblique manner. While displaying, it is also hoped that the displayed two-dimensional images can be annotated so that the annotated areas can be obtained for the next step of medical or scientific research.
[0003] Since medical images are often a sequence of multiple images, multiple layers of medical images are superimposed into a 3D volume. The existing annotation method is often to annotate 2D medical images layer by layer, and multiple 2D annotation layers are superimposed to form a 3D region of interest volume. On oblique 2D images, annotation is currently very complicated, and there are currently no successful annotation cases on mainstream software. Summary of the invention
[0004] In order to overcome the problems existing in the related art, the present disclosure provides a method for acquiring a region of interest of a medical image, an apparatus for acquiring a region of interest of a medical image, a computer-readable storage medium, and an electronic device.
[0005] According to a first aspect of an embodiment of the present disclosure, a method for acquiring a region of interest of a medical image is provided, the method comprising:
[0006] Acquiring a medical image, and performing section processing on the medical image to obtain a two-dimensional image;
[0007] Acquire the coordinates of a first vertex of a target graphic in the first coordinate system, and perform coordinate transformation processing on the first vertex coordinates to obtain the coordinates of a second vertex in a second coordinate system, wherein the target graphic is used to determine the region of interest of the medical image in the two-dimensional image;
[0008] A coordinate range is determined according to the second vertex coordinates, and an offset process is performed according to the coordinate range to obtain the region of interest.
[0009] Optionally, the performing section processing on the medical image to obtain a two-dimensional image includes:
[0010] Acquire a distance between a second image coordinate of the medical image in a second coordinate system and the second coordinate system;
[0011] Determine the first image coordinates of the medical image in the first coordinate system according to the second image coordinates and the distance;
[0012] The medical image is subjected to section processing to obtain a two-dimensional image, and image coordinates of the two-dimensional image are determined according to the first image coordinates.
[0013] Optionally, obtaining the coordinates of a first vertex of the target graphic in the first coordinate system includes:
[0014] Determine the first graphic coordinates of the target graphic in the first coordinate system according to the image coordinates, and obtain the second graphic coordinates of the target graphic in the first coordinate system;
[0015] A target radius corresponding to the target graphic is determined according to the first graphic coordinates and the second graphic coordinates, and a first vertex coordinate is determined according to the first graphic coordinates and the target radius.
[0016] Optionally, determining first graphic coordinates of the target graphic in the first coordinate system according to the image coordinates includes:
[0017] Determine the two-dimensional graphic coordinates of the target graphic according to the image coordinates;
[0018] The two-dimensional graphic coordinates are dimensionally transformed to obtain first graphic coordinates of the target graphic in the first coordinate system.
[0019] Optionally, performing offset processing according to the coordinate range to obtain the region of interest includes:
[0020] Acquire the third graphic coordinates of the target graphic, and perform initial offset processing in the second coordinate system according to the third graphic coordinates to obtain a first set;
[0021] Performing iterative offset processing according to the coordinate range to obtain a second set, where the second set is mutually exclusive with the first set;
[0022] The region of interest is obtained by performing traversal and offset processing according to the coordinate range.
[0023] Optionally, the acquiring the third graphic coordinates of the target graphic includes:
[0024] Acquire first graphic coordinates of the target graphic in the first coordinate system;
[0025] The first graphic coordinates are subjected to coordinate transformation processing to obtain third graphic coordinates.
[0026] Optionally, performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain the first set includes:
[0027] Performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain target offset coordinates;
[0028] A target pixel value at the target offset coordinate is obtained, and according to the target pixel value, the target offset coordinate is determined to be recorded as the first set.
[0029] Optionally, performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain target offset coordinates includes:
[0030] Performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain second offset coordinates, and performing coordinate conversion processing on the second offset coordinates to obtain first offset coordinates in the first coordinate system;
[0031] Acquire a target radius corresponding to the target graphic, and determine a coordinate distance according to the first offset coordinate and the first graphic coordinate;
[0032] The coordinate distance and the target radius are compared to obtain a comparison result, and the second offset coordinate is determined as the target offset coordinate according to the comparison result.
[0033] According to a second aspect of an embodiment of the present disclosure, there is provided a device for acquiring a region of interest of a medical image, comprising:
[0034] An image sectioning module is configured to acquire a medical image and perform sectioning processing on the medical image to obtain a two-dimensional image;
[0035] a coordinate conversion module, configured to obtain first vertex coordinates of a target graphic in the first coordinate system, and perform coordinate conversion processing on the first vertex coordinates to obtain second vertex coordinates in a second coordinate system, wherein the target graphic is used to determine a region of interest of the medical image in the two-dimensional image;
[0036] The region acquisition module is configured to determine a coordinate range according to the second vertex coordinates, and perform offset processing according to the coordinate range to obtain the region of interest.
[0037] Optionally, the image section module is configured as follows:
[0038] Acquire a distance between a second image coordinate of the medical image in a second coordinate system and the second coordinate system;
[0039] Determine the first image coordinates of the medical image in the first coordinate system according to the second image coordinates and the distance;
[0040] The medical image is subjected to section processing to obtain a two-dimensional image, and image coordinates of the two-dimensional image are determined according to the first image coordinates.
[0041] Optionally, the coordinate conversion module is configured as follows:
[0042] Determine the first graphic coordinates of the target graphic in the first coordinate system according to the image coordinates, and obtain the second graphic coordinates of the target graphic in the first coordinate system;
[0043] A target radius corresponding to the target graphic is determined according to the first graphic coordinates and the second graphic coordinates, and a first vertex coordinate is determined according to the first graphic coordinates and the target radius.
[0044] Optionally, the coordinate conversion module is configured as follows:
[0045] Determine the two-dimensional graphic coordinates of the target graphic according to the image coordinates;
[0046] The two-dimensional graphic coordinates are dimensionally transformed to obtain first graphic coordinates of the target graphic in the first coordinate system.
[0047] Optionally, the region acquisition module is configured to:
[0048] Acquire the third graphic coordinates of the target graphic, and perform initial offset processing in the second coordinate system according to the third graphic coordinates to obtain a first set;
[0049] Performing iterative offset processing according to the coordinate range to obtain a second set, where the second set is mutually exclusive with the first set;
[0050] The region of interest is obtained by performing traversal and offset processing according to the coordinate range.
[0051] Optionally, the region acquisition module is configured to:
[0052] Acquire first graphic coordinates of the target graphic in the first coordinate system;
[0053] The first graphic coordinates are subjected to coordinate transformation processing to obtain third graphic coordinates.
[0054] Optionally, the region acquisition module is configured to:
[0055] Performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain target offset coordinates;
[0056] A target pixel value at the target offset coordinate is obtained, and according to the target pixel value, the target offset coordinate is determined to be recorded as the first set.
[0057] Optionally, the region acquisition module is configured to:
[0058] Performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain second offset coordinates, and performing coordinate conversion processing on the second offset coordinates to obtain first offset coordinates in the first coordinate system;
[0059] Acquire a target radius corresponding to the target graphic, and determine a coordinate distance according to the first offset coordinate and the first graphic coordinate;
[0060] The coordinate distance and the target radius are compared to obtain a comparison result, and the second offset coordinate is determined as the target offset coordinate according to the comparison result.
[0061] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of any one of the methods for acquiring a region of interest in a medical image provided in the first aspect of the present disclosure are implemented.
[0062] According to a fourth aspect of an embodiment of the present disclosure, there is provided an electronic device, including:
[0063] processor;
[0064] a memory for storing processor-executable instructions;
[0065] The processor is configured to: execute the executable instructions to implement any one of the steps of the method for acquiring a region of interest of a medical image provided in the first aspect of the present disclosure.
[0066] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:
[0067] In the method and apparatus provided by the exemplary embodiments of the present disclosure, the coordinate range constraint is obtained by converting the first vertex coordinates in the first coordinate system into the second vertex coordinates in the second coordinate system, and the region of interest is obtained by performing offset processing within the coordinate range. In the case of any oblique medical image, the three-dimensional region of interest can be determined from the two-dimensional image according to the user's intention, ensuring that the region of interest fully conforms to the user's true intention, and the determination method and the determined range are accurate and efficient, providing a real and reliable implementation method for determining the region of interest of the oblique medical image.
[0068] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0069] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0070] Figure 1 A schematic diagram of an interface for obliquely cutting a sagittal plane in the related art is schematically shown;
[0071] Figure 2 Another interface diagram of an oblique sagittal plane in the related art is schematically shown;
[0072] Figure 3 A schematic diagram of a process of obtaining a region of interest of a medical image in an exemplary embodiment of the present disclosure is schematically shown;
[0073] Figure 4 A schematic diagram of a process of performing section processing on a medical image in an exemplary embodiment of the present disclosure is schematically shown;
[0074] Figure 5 Schematically showing the interface diagram of the external cube in two coordinate systems in an exemplary embodiment of the present disclosure;
[0075] Figure 6 A schematic diagram of a process of obtaining the coordinates of the first vertex of a target graphic in an exemplary embodiment of the present disclosure is schematically shown;
[0076] Figure 7 A schematic diagram schematically shows a flow chart of a method for obtaining first graphic coordinates in an exemplary embodiment of the present disclosure;
[0077] Figure 8 A schematic diagram of a flow chart of a method for performing offset processing according to a coordinate range in an exemplary embodiment of the present disclosure is schematically shown;
[0078] Fig. 9 A schematic diagram schematically shows a flow chart of a method for obtaining third graphic coordinates in an exemplary embodiment of the present disclosure;
[0079] Fig.10 A schematic flow chart schematically illustrates a method for performing initial offset processing according to third graphic coordinates in an exemplary embodiment of the present disclosure;
[0080] Fig.11 A schematic diagram schematically illustrates a flow chart of a method for determining target offset coordinates in an exemplary embodiment of the present disclosure;
[0081] Fig.12A schematic diagram of the neighborhood composition of a voxel in an index coordinate system in an exemplary embodiment of the present disclosure is schematically shown;
[0082] Fig.13 A schematic diagram schematically illustrates a traversal from a starting point to an ending point in an exemplary embodiment of the present disclosure;
[0083] Fig.14 A schematic diagram schematically shows a structure of a device for acquiring a region of interest of a medical image in an exemplary embodiment of the present disclosure;
[0084] Fig.15 A schematic diagram schematically shows the structure of another device for acquiring a region of interest of a medical image in an exemplary embodiment of the present disclosure;
[0085] Fig.16 A schematic diagram of the structure of another apparatus for acquiring a region of interest of a medical image in an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION
[0086] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0087] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.
[0088] Medical image MPR is a two-dimensional image converted from multiple layers of medical images at different viewing angles, which are usually divided into coronal, sagittal and axial planes. With the advancement of hardware technology, it is now possible to display the coronal, sagittal and axial planes in an oblique manner. While displaying, it is also hoped that the displayed two-dimensional image can be annotated so that the annotated area can be obtained for the next step of medical or scientific research.
[0089] Among them, MPR in medical imaging is a technology that generates two-dimensional images of different planes by processing three-dimensional image data obtained by CT (Computed Tomography) or MRI (Magnetic Resonance Imaging) scanning.
[0090] This technology allows doctors to view internal structures from multiple angles, such as cross-sectional, sagittal and coronal planes, without having to perform multiple scans. MPR images help diagnose diseases and plan surgeries more accurately.
[0091] Figure 1 FIG. 4 shows a schematic diagram of an interface for obliquely cutting a sagittal plane in the related art, such as Figure 1 As shown, the MPR of medical images is generally tangent, but when the medical images form a three-dimensional volume, a two-dimensional image can be obtained at any angle by viewing it with a camera.
[0092] Since medical images are often a sequence of multiple images, multiple layers of medical images are superimposed into a 3D volume. The existing annotation method is often to annotate 2D medical images layer by layer, and multiple 2D annotation layers are superimposed to form a 3D region of interest volume. On oblique 2D images, annotation is currently very complicated, and there are currently no successful annotation cases on mainstream software.
[0093] Figure 2 Another interface schematic diagram of an oblique cut sagittal plane in the related art is shown, Figure 2 As shown, not every point in an image at any angle is a valid point, and because the spacing of each coordinate axis of a medical image is different, the real voxel 3D volume is a cuboid, not a cube. The spacing in each direction on the oblique section is also different.
[0094] When processing CT images, the selected layer is divided into several cubes of equal volume, which are called voxels.
[0095] When marking, the user's brush is often a circle, which is painted on the surface of the two-dimensional image. The circle of the tool in the user's hand has different spacing in each direction, so the number of voxels actually contained in each direction is actually different. At this time, the range of the user's painting needs to be recalculated to truly reflect the user's true intention.
[0096] In view of the problems existing in the related art, the present disclosure provides a method for obtaining a region of interest of a medical image. Figure 3 is a flow chart of a method for obtaining a region of interest in a medical image according to an exemplary embodiment. Figure 3 As shown, the method may at least include the following steps:
[0097] Step S310: Obtain a medical image and perform section processing on the medical image to obtain a two-dimensional image.
[0098] Step S320. Obtain the first vertex coordinates of the target graphic in the first coordinate system, and perform coordinate transformation processing on the first vertex coordinates to obtain the second vertex coordinates in the second coordinate system. The target graphic is used to determine the region of interest of the medical image in the two-dimensional image.
[0099] Step S330: Determine a coordinate range according to the coordinates of the second vertex, and perform offset processing according to the coordinate range to obtain a region of interest.
[0100] In an exemplary embodiment of the present disclosure, the coordinate range constraint is obtained by converting the first vertex coordinate in the first coordinate system into the second vertex coordinate in the second coordinate system, and the region of interest is obtained by performing offset processing within the coordinate range. In the case of any oblique medical image, the three-dimensional region of interest can be determined from the two-dimensional image according to the user's intention, ensuring that the region of interest fully conforms to the user's true intention, and the determination method and the determined range are accurate and efficient, providing a real and reliable implementation method for determining the region of interest of the oblique medical image.
[0101] The following describes in detail the steps of the method for obtaining the region of interest of a medical image.
[0102] In step S310, a medical image is acquired and section processing is performed on the medical image to obtain a two-dimensional image.
[0103] In an exemplary embodiment of the present disclosure, the medical image is a three-dimensional image.
[0104] In an alternative embodiment, Figure 4 A schematic diagram of a process for processing a section of a medical image is shown. Figure 4 As shown, the method may at least include the following steps: In step S410, the second image coordinates of the medical image in the second coordinate system and the distance between the second coordinate system are obtained.
[0105] The second coordinate system may be an index coordinate system.
[0106] When a three-dimensional medical image is placed in a world scene, the index coordinates of the medical image in the index coordinate system and the distances between the three axes X, Y, and Z may be obtained as the second image coordinates and the distance, respectively.
[0107] In step S420, first image coordinates of the medical image in the first coordinate system are determined according to the second image coordinates and the distance.
[0108] After obtaining the second image coordinates and spacing, the second image coordinates and spacing can be multiplied respectively, and the calculation results are added to the corresponding origin coordinates to obtain the corresponding first image coordinates. The first image coordinates are the coordinates of the medical image in the world coordinate system. Therefore, the first coordinate system can be the world coordinate system.
[0109] In step S430, the medical image is subjected to section processing to obtain a two-dimensional image, and the image coordinates of the two-dimensional image are determined according to the first image coordinates.
[0110] Furthermore, in the dimension of the world coordinate system, a three-dimensional medical image can be sectioned to obtain an image of the medical image displayed on a two-dimensional plane as a two-dimensional image.
[0111] Since the first image coordinates of the medical image in the world coordinate system are known, after the two-dimensional image is obtained on the section, the image coordinates corresponding to the two-dimensional image can be calculated according to the first image coordinates.
[0112] In step S320, the first vertex coordinates of the target graphic in the first coordinate system are obtained, and the first vertex coordinates are transformed to obtain the second vertex coordinates in the second coordinate system. The target graphic is used to determine the region of interest of the medical image in the two-dimensional image.
[0113] In an exemplary embodiment of the present disclosure, when a user drags the edge of a circle formed by a brush on an inclined sagittal plane to zoom in and out of a selected range of interest, the center of the circle of the user's dragging operation can be determined, and the center position is actually the center position of the sphere.
[0114] Figure 5 The schematic diagram of the interface of the external cube in two coordinate systems is shown, Figure 5 As shown in the figure, observing the two coordinate systems, we can find that in the world coordinate system on the right, the radius of the sphere is the same; in the index coordinate system on the left, the sphere is an ellipsoid. Under the premise of a perfect sphere, if the oblique section passes through the center of the sphere, a perfect circle can be obtained at any angle. Therefore, a perfect sphere is required when operating here.
[0115] In an alternative embodiment, Figure 6 A schematic diagram of a process for obtaining the coordinates of the first vertex of a target graphic is shown. Figure 6 As shown, the method may at least include the following steps: in step S610, first graphic coordinates of the target graphic in the first coordinate system are determined according to the image coordinates, and second graphic coordinates of the target graphic in the first coordinate system are acquired.
[0116] In an alternative embodiment, Figure 7 A schematic flow chart of a method for obtaining the first graphic coordinates is shown, Figure 7As shown, the method may at least include the following steps: In step S710, the two-dimensional graphic coordinates of the target graphic are determined according to the image coordinates.
[0117] The target graphic may be a circle formed when the user's brush is put down, or other graphics formed by the brush, which is not particularly limited in this exemplary embodiment.
[0118] Since the image coordinates of the two-dimensional image are known, the two-dimensional image coordinates of the target image can be obtained according to the position of the target image on the two-dimensional image.
[0119] In step S720, dimension conversion is performed on the two-dimensional graphic coordinates to obtain first graphic coordinates of the target graphic in the first coordinate system.
[0120] After obtaining the two-dimensional graphic coordinates, the two-dimensional graphic coordinates can be dimensionally converted to obtain the first graphic coordinates of the target graphic in the three-dimensional coordinate system of the world coordinate system, and the first graphic coordinates can be expressed as the world coordinates of the center O of the sphere.
[0121] As the user drags the brush to change the radius of the covered circle, the coordinates of point A, which the user drags to the two-dimensional plane position, can be obtained. According to the perspective camera, the world coordinates A of point A can be determined accordingly. world as the second graphic coordinates.
[0122] Specifically, according to formula (1):
[0123]
[0124] It can be seen that
[0125]
[0126] Among them, projectionMatrix is the projection matrix of the camera, matrixWorldInverse is the viewport transformation matrix of the camera, X and Y are the coordinates of point A in two dimensions, and Z is generally 0.
[0127] In step S620, a target radius corresponding to the target graphic is determined according to the first graphic coordinates and the second graphic coordinates, and a first vertex coordinate is determined according to the first graphic coordinates and the target radius.
[0128] Further, according to the first graphic coordinate O of the sphere center O world and the second graphic coordinate A world , and the three-dimensional Euclidean distance formula The radius of the sphere in the world coordinate system can be obtained as shown in formula (3):
[0129]
[0130] Among them, O world =[X O ,Y O ,Z O ], A world =[X A ,Y A ,Z A ].
[0131] Furthermore, according to the target radius R world Calculate the world coordinates of the six vertices where the sphere and the circumscribed cube intersect, as the first vertex coordinates.
[0132] Specifically, the coordinates of the six first vertices are:
[0133] TOP world =[O world .X+R world ,O world .Y,O world .Z]
[0134] BOTTOM world =[O world .XR world ,O world .Y,O world .Z]
[0135] LEFT world =[O world .X,O world .YR world ,O world .Z]
[0136] RIGHT world =[O world .X,O world .Y+R world ,O world .Z]
[0137] FRONT world =[O world .X,O world .Y,O world .ZR world ]
[0138] BACK world =[O world .X,O world .Y,O world .Z+R world ]
[0139] After the first vertex coordinates are acquired, coordinate conversion processing may be performed on the first vertex coordinates to obtain corresponding second vertex coordinates in the index coordinate system.
[0140] According to the world coordinates of the six vertices, use the perspective camera to convert the six world coordinates into six index coordinates TOP index , BOTTOM index , LEFT index 、RIGHT index 、FRONT index and BACK index .
[0141] Specifically, the following formulas (4)-(7) can be used for coordinate transformation:
[0142]
[0143] Among them, R is the rotation matrix of the camera, R -1 is the inverse matrix of the rotation matrix, P local is the calculated intermediate value, X box , Y box and Z box is the length of the bounding box of the 3D medical image on the X, Y, and Z axes, with a maximum value of 1. Dim , Y Dim , Z Dim are the length, width and number of three-dimensional medical images respectively.
[0144] In addition, the second vertex coordinates may be obtained by subtracting the origin coordinates from the first vertex coordinates and dividing the result by the spacing on the corresponding axis, or other coordinate conversion processing methods may be used, which is not particularly limited in this exemplary embodiment.
[0145] In step S330, a coordinate range is determined according to the coordinates of the second vertex, and an offset process is performed according to the coordinate range to obtain a region of interest.
[0146] In an exemplary embodiment of the present disclosure, after obtaining the six second vertex coordinates corresponding to the first vertex coordinates, the minimum values of the three axes X, Y, and Z can be obtained from the six second vertex coordinates to form an index coordinate point, which is the starting point of the circumscribed cube [X_Index min , Y_Index min , Z_Index min ].
[0147] Further, the maximum values of the three axes X, Y, and Z are obtained from the six second vertex coordinates [X_Index max , Y_Index max , Z_Indexmax ] forms another index coordinate point, which is the end point of the circumscribed cuboid in the index coordinate system.
[0148] It is worth noting that the circumscribed cuboid in the index coordinate system is a cube in the world coordinate system.
[0149] Therefore, after determining the starting point of the circumscribed cube and the ending point of the circumscribed cuboid, the index coordinate points between the starting point of the circumscribed cube and the ending point of the circumscribed cuboid can be determined as the coordinate range in the index coordinate system.
[0150] In an alternative embodiment, Figure 8 A schematic diagram of a method for performing offset processing according to a coordinate range is shown, such as Figure 8 As shown, the method may at least include the following steps: In step S810, the third graphic coordinates of the target graphic are acquired, and an initial offset process is performed in the second coordinate system according to the third graphic coordinates to obtain a first set.
[0151] In an alternative embodiment, Fig. 9 A schematic flow chart of a method for obtaining the third graphic coordinates is shown, such as Fig. 9 As shown, the method may at least include the following steps: In step S910, the first graphic coordinates of the target graphic in the first coordinate system are obtained.
[0152] The first graphic coordinates are represented as the world coordinates of the sphere center O.
[0153] In step S920, coordinate transformation processing is performed on the first graphic coordinates to obtain third graphic coordinates.
[0154] Furthermore, the coordinates of the first graphic are transformed according to formulas (4)-(7) to obtain the corresponding third graphic coordinates in the second coordinate system. The center index coordinate O index express.
[0155] In addition, the third graphic coordinates may be obtained by subtracting the origin coordinates from the first graphic coordinates and dividing the result by the spacing on the corresponding axis, or other coordinate conversion processing methods may be used, which is not specifically limited in this exemplary embodiment.
[0156] In an alternative embodiment, Fig.10 A schematic flow chart of a method for performing initial offset processing according to the third graphic coordinates is shown. Fig.10 As shown, the method may at least include the following steps: In step S1010, initial offset processing is performed in the second coordinate system according to the third graphic coordinates to obtain target offset coordinates.
[0157] In an alternative embodiment, Fig.11A schematic diagram of a method for determining target offset coordinates is shown in FIG. Fig.11 As shown, the method may include at least the following steps: in step S1110, initial offset processing is performed in the second coordinate system according to the third graphic coordinates to obtain second offset coordinates, and coordinate transformation processing is performed on the second offset coordinates to obtain first offset coordinates in the first coordinate system.
[0158] Fig.12 A schematic diagram of the neighborhood structure of a voxel in the index coordinate system is shown, Fig.12 As shown, the cube is divided into 27 equal parts, and thus each voxel has 26 neighbors around it.
[0159] Therefore, after obtaining the third graphic coordinates, the coordinate O can be indexed from the center of the circle. index Initially, an offset is made to any position in the surrounding 26 neighborhoods to obtain a second offset coordinate in the index coordinate system, and the second offset coordinate is within the coordinate range.
[0160] Furthermore, the second offset coordinates are converted into the world coordinate system to obtain the first offset coordinates.
[0161] Specifically, the following formulas (8)-(11) can be used for coordinate transformation:
[0162]
[0163] Among them, R is the rotation matrix of the camera, X box , Y box and Z box is the length of the bounding box of the 3D medical image on the X, Y, and Z axes, with a maximum value of 1. Dim , Y Dim , Z Dim are the length, width and number of three-dimensional medical images respectively.
[0164] In step S1120, a target radius corresponding to the target graphic is obtained, and a coordinate distance is determined according to the first offset coordinates and the first graphic coordinates.
[0165] The target radius is the radius of the sphere in the world coordinate system.
[0166] The coordinate distance between the first offset coordinate and the first graphic coordinate can be calculated according to the three-dimensional Euclidean distance formula.
[0167] In step S1130, the coordinate distance and the target radius are compared to obtain a comparison result, and the second offset coordinate is determined as the target offset coordinate according to the comparison result.
[0168] Further, the coordinate distance and the target radius are compared to obtain a comparison result.
[0169] When the comparison result is that the coordinate distance is less than the target radius, it indicates that the first offset coordinate is within the positive sphere of the world coordinate system, and the corresponding second offset coordinate can be determined as the target offset coordinate.
[0170] In step S1020, the target pixel value at the target offset coordinate is obtained, and the target offset coordinate is recorded as a first set according to the target pixel value.
[0171] After the second offset coordinate is determined as the target offset coordinate, the pixel value in the voxel at the position represented by the target offset coordinate may be acquired in the medical image as the target pixel value.
[0172] Further, it is determined whether the target pixel value is within the range that the user wishes to select.
[0173] For example, when the medical image is an image of a blood vessel region, the pixel value of the blood vessel region is between 200-500, then, when the target pixel value is within this interval, it indicates that the target pixel value is within the range that the user wishes to select, and the target offset coordinates can be recorded as the coordinates in the first set. On the contrary, when the target pixel value is not within this interval, it indicates that the target pixel value is not within the range that the user wishes to select, and the target offset coordinates are not recorded as the coordinates in the first set.
[0174] In this way, it is possible to iterate sequentially until the boundary of the coordinate range is reached, and all valid target offset coordinates are recorded to form an index coordinate point set V1 as the first set.
[0175] In step S820, an iterative offset process is performed according to the coordinate range to obtain a second set, and the second set is mutually exclusive with the first set.
[0176] Fig.13 A schematic diagram of traversal from the starting point to the end point is shown, as Fig.13 As shown, again from the starting point of the circumscribed cuboid [X_Index min , Y_Index min , Z_Index min ], toward the end point [X_Index max , Y_Index max , Z_Indexmax] are iterated and offset in sequence. When an index coordinate point in the first set V1 is encountered, the iteration is terminated to obtain an index coordinate point set V2 as the second set.
[0177] In step S830, a traversal offset process is performed according to the coordinate range to obtain a region of interest.
[0178] and Fig.13Similarly, again from the starting point of the circumscribed cuboid [X_Index min , Y_Index min , Z_Indexmin] and move to the end point [X_Index max , Y_Index max , Z_Indexmax] traverses the offset in turn, excluding all points in the index coordinate point set V2 to obtain the coordinate index point set V3. The set V3 is the intended area of the user's brush radius, and V3 forms a spherical outline without holes as the region of interest. Moreover, the region of interest is a circle on the two-dimensional image of the MPR plane and the oblique section at any angle, which is consistent with the shape of the user's brush.
[0179] The region obtained in set V3 is the region that the user actually wants. Using set V3 for annotation fits the user's brush, and even if the angle of the oblique sagittal plane is changed, it will fit. In this way, the three-dimensional region of interest that the user actually intended is obtained from the two-dimensional image of the oblique sagittal plane.
[0180] In summary, the two coordinate systems are mapped to each other to obtain the spherical constraint in the world coordinate system, and then the coordinate constraint in the three-dimensional index coordinate system is obtained through the two-dimensional operation plane, so that the subsequent algorithm coordinate limitation of the region of interest is accurate and efficient. When the region of interest is limited by the algorithm, the real hole-free area is obtained through two exclusion algorithms, which meets the user's real intention and makes the result efficient and accurate.
[0181] In an exemplary embodiment of the present disclosure, the coordinate range constraint is obtained by converting the first vertex coordinates in the first coordinate system into the second vertex coordinates in the second coordinate system, and the region of interest is obtained by performing an offset process within the coordinate range. In the case of any oblique medical image, the three-dimensional region of interest can be determined from the two-dimensional image according to the user's intention, ensuring that the region of interest fully conforms to the user's true intention, and the determination method and the determined range are accurate and efficient, providing a real and reliable implementation method for determining the region of interest of the oblique medical image. Even if the angle of the oblique sagittal plane is changed, the range of the region of interest is still accurately fitted, with extremely high accuracy.
[0182] In addition, in an exemplary embodiment of the present disclosure, a device for acquiring a region of interest of a medical image is also provided. Fig.14 A schematic diagram of the structure of a device for acquiring a region of interest of a medical image is shown. Fig.14 As shown, the device 1400 for acquiring a region of interest of a medical image may include: an image section module 1410, a coordinate conversion module 1420 and a region acquisition module 1430. Among them:
[0183] The image sectioning module 1410 is configured to acquire a medical image and perform sectioning processing on the medical image to obtain a two-dimensional image;
[0184] A coordinate conversion module 1420 is configured to obtain the first vertex coordinates of a target graphic in the first coordinate system, and perform coordinate conversion processing on the first vertex coordinates to obtain the second vertex coordinates in the second coordinate system, wherein the target graphic is used to determine the region of interest of the medical image in the two-dimensional image;
[0185] The region acquisition module 1430 is configured to determine a coordinate range according to the second vertex coordinates, and perform an offset process according to the coordinate range to obtain the region of interest.
[0186] In some embodiments of the present disclosure, the image section module 1410 is configured to:
[0187] Acquire a distance between a second image coordinate of the medical image in a second coordinate system and the second coordinate system;
[0188] Determine the first image coordinates of the medical image in the first coordinate system according to the second image coordinates and the distance;
[0189] The medical image is subjected to section processing to obtain a two-dimensional image, and image coordinates of the two-dimensional image are determined according to the first image coordinates.
[0190] In some embodiments of the present disclosure, the coordinate conversion module 1420 is configured to:
[0191] Determine the first graphic coordinates of the target graphic in the first coordinate system according to the image coordinates, and obtain the second graphic coordinates of the target graphic in the first coordinate system;
[0192] A target radius corresponding to the target graphic is determined according to the first graphic coordinates and the second graphic coordinates, and a first vertex coordinate is determined according to the first graphic coordinates and the target radius.
[0193] In some embodiments of the present disclosure, the coordinate conversion module 1420 is configured to:
[0194] Determine the two-dimensional graphic coordinates of the target graphic according to the image coordinates;
[0195] The two-dimensional graphic coordinates are dimensionally transformed to obtain first graphic coordinates of the target graphic in the first coordinate system.
[0196] In some embodiments of the present disclosure, the region acquisition module 1430 is configured to:
[0197] Acquire the third graphic coordinates of the target graphic, and perform initial offset processing in the second coordinate system according to the third graphic coordinates to obtain a first set;
[0198] Performing iterative offset processing according to the coordinate range to obtain a second set, where the second set is mutually exclusive with the first set;
[0199] The region of interest is obtained by performing traversal and offset processing according to the coordinate range.
[0200] In some embodiments of the present disclosure, the region acquisition module 1430 is configured to:
[0201] Acquire first graphic coordinates of the target graphic in the first coordinate system;
[0202] The first graphic coordinates are subjected to coordinate transformation processing to obtain third graphic coordinates.
[0203] In some embodiments of the present disclosure, the region acquisition module 1430 is configured to:
[0204] Performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain target offset coordinates;
[0205] A target pixel value at the target offset coordinate is obtained, and according to the target pixel value, the target offset coordinate is determined to be recorded as the first set.
[0206] In some embodiments of the present disclosure, the region acquisition module 1430 is configured to:
[0207] Performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain second offset coordinates, and performing coordinate conversion processing on the second offset coordinates to obtain first offset coordinates in the first coordinate system;
[0208] Acquire a target radius corresponding to the target graphic, and determine a coordinate distance according to the first offset coordinate and the first graphic coordinate;
[0209] The coordinate distance and the target radius are compared to obtain a comparison result, and the second offset coordinate is determined as the target offset coordinate according to the comparison result.
[0210] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0211] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the method for acquiring a region of interest of a medical image provided by the present disclosure.
[0212] Fig.15 1 is a block diagram of another apparatus 1500 for acquiring a region of interest of a medical image according to an exemplary embodiment. For example, the apparatus 1500 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.
[0213] Reference Fig.15 , the device 1500 may include one or more of the following components: a processing component 1502 , a memory 1504 , a power component 1506 , a multimedia component 1508 , an audio component 1510 , an input / output interface 1512 , a sensor component 1514 , and a communication component 1516 .
[0214] The processing component 1502 generally controls the overall operation of the device 1500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1502 may include one or more processors 1520 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 1502 may include one or more modules to facilitate the interaction between the processing component 1502 and other components. For example, the processing component 1502 may include a multimedia module to facilitate the interaction between the multimedia component 1508 and the processing component 1502.
[0215] The memory 1504 is configured to store various types of data to support the operation of the device 1500. Examples of such data include instructions for any application or method operating on the device 1500, contact data, phone book data, messages, pictures, videos, etc. The memory 1504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
[0216] The power supply component 1506 provides power to the various components of the device 1500. The power supply component 1506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 1500.
[0217] The multimedia component 1508 includes a screen that provides an output interface between the device 1500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1508 includes a front camera and / or a rear camera. When the device 1500 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
[0218] The audio component 1510 is configured to output and / or input audio signals. For example, the audio component 1510 includes a microphone (MIC), and when the device 1500 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1504 or sent via the communication component 1516. In some embodiments, the audio component 1510 also includes a speaker for outputting audio signals.
[0219] The input / output interface 1512 provides an interface between the processing component 1502 and the peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.
[0220] The sensor assembly 1514 includes one or more sensors for providing various aspects of the status assessment of the device 1500. For example, the sensor assembly 1514 can detect the open / closed state of the device 1500, the relative positioning of components, such as the display and keypad of the device 1500, the sensor assembly 1514 can also detect the position change of the device 1500 or a component of the device 1500, the presence or absence of user contact with the device 1500, the orientation or acceleration / deceleration of the device 1500, and the temperature change of the device 1500. The sensor assembly 1514 can include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1514 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1514 can also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
[0221] The communication component 1516 is configured to facilitate wired or wireless communication between the device 1500 and other devices. The device 1500 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1516 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1516 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
[0222] In an exemplary embodiment, the apparatus 1500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above methods.
[0223] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1504 including instructions, and the instructions can be executed by the processor 1520 of the device 1500 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
[0224] In addition to being an independent electronic device, the above-mentioned device can also be a part of an independent electronic device. For example, in one embodiment, the device can be an integrated circuit (IC) or a chip, wherein the integrated circuit can be an IC or a collection of multiple ICs; the chip can include but is not limited to the following types: GPU (Graphics Processing Unit), CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), SOC (System on Chip, SoC), etc. The above-mentioned integrated circuit or chip can be used to execute executable instructions (or codes) to implement the above-mentioned method of acquiring the region of interest of the medical image. The executable instructions can be stored in the integrated circuit or chip, or can be obtained from other devices or equipment, for example, the integrated circuit or chip includes a processor, a memory, and an interface for communicating with other devices. The executable instruction can be stored in the memory, and when the executable instruction is executed by the processor, the above-mentioned method of acquiring the region of interest of the medical image is implemented; alternatively, the integrated circuit or chip can receive the executable instruction through the interface and transmit it to the processor for execution, so as to implement the above-mentioned method.
[0225] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned method for acquiring a region of interest of a medical image when executed by the programmable device.
[0226] Fig.16 1 is a block diagram of another apparatus 1600 for acquiring a region of interest of a medical image according to an exemplary embodiment. For example, the apparatus 1600 may be provided as a server. Fig.16 The apparatus 1600 includes a processing component 1622, which further includes one or more processors, and a memory resource represented by a memory 1632 for storing instructions executable by the processing component 1622, such as an application. The application stored in the memory 1632 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1622 is configured to execute instructions to perform the above-mentioned method for acquiring a region of interest of a medical image.
[0227] The device 1600 may also include a power supply component 1626 configured to perform power management of the device 1600, a wired or wireless network interface 1650 configured to connect the device 1600 to a network, and an input / output interface 1658. The device 1600 may operate based on an operating system stored in the memory 1632.
[0228] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.
[0229] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. A method for obtaining a region of interest in a medical image, characterized in that: include: Acquiring a medical image, and performing section processing on the medical image to obtain a two-dimensional image; Acquire the coordinates of a first vertex of a target graphic in the first coordinate system, and perform coordinate transformation processing on the first vertex coordinates to obtain the coordinates of a second vertex in a second coordinate system, wherein the target graphic is used to determine the region of interest of the medical image in the two-dimensional image; A coordinate range is determined according to the second vertex coordinates, and an offset process is performed according to the coordinate range to obtain the region of interest.
2. The method for obtaining a region of interest of a medical image according to claim 1, characterized in that: The step of performing section processing on the medical image to obtain a two-dimensional image includes: Acquire a distance between a second image coordinate of the medical image in a second coordinate system and the second coordinate system; Determine the first image coordinates of the medical image in the first coordinate system according to the second image coordinates and the distance; The medical image is subjected to section processing to obtain a two-dimensional image, and image coordinates of the two-dimensional image are determined according to the first image coordinates.
3. The method for obtaining a region of interest of a medical image according to claim 2, characterized in that: The obtaining the first vertex coordinates of the target graphic in the first coordinate system includes: Determine the first graphic coordinates of the target graphic in the first coordinate system according to the image coordinates, and obtain the second graphic coordinates of the target graphic in the first coordinate system; A target radius corresponding to the target graphic is determined according to the first graphic coordinates and the second graphic coordinates, and a first vertex coordinate is determined according to the first graphic coordinates and the target radius.
4. The method for obtaining a region of interest of a medical image according to claim 3, characterized in that: The step of determining the first graphic coordinates of the target graphic in the first coordinate system according to the image coordinates includes: Determine the two-dimensional graphic coordinates of the target graphic according to the image coordinates; The two-dimensional graphic coordinates are dimensionally transformed to obtain first graphic coordinates of the target graphic in the first coordinate system.
5. The method for obtaining a region of interest of a medical image according to claim 1, characterized in that: The performing offset processing according to the coordinate range to obtain the region of interest includes: Acquire the third graphic coordinates of the target graphic, and perform initial offset processing in the second coordinate system according to the third graphic coordinates to obtain a first set; Performing iterative offset processing according to the coordinate range to obtain a second set, where the second set is mutually exclusive with the first set; The region of interest is obtained by performing traversal and offset processing according to the coordinate range.
6. The method for obtaining a region of interest of a medical image according to claim 5, characterized in that: The obtaining of the third graphic coordinates of the target graphic comprises: Acquire first graphic coordinates of the target graphic in the first coordinate system; The first graphic coordinates are subjected to coordinate transformation processing to obtain third graphic coordinates.
7. The method for obtaining a region of interest of a medical image according to claim 6, characterized in that: The step of performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain the first set includes: Performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain target offset coordinates; A target pixel value at the target offset coordinate is obtained, and according to the target pixel value, the target offset coordinate is determined to be recorded as the first set.
8. The method for obtaining a region of interest of a medical image according to claim 7, characterized in that: The performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain target offset coordinates includes: Performing initial offset processing in the second coordinate system according to the third graphic coordinates to obtain second offset coordinates, and performing coordinate conversion processing on the second offset coordinates to obtain first offset coordinates in the first coordinate system; Acquire a target radius corresponding to the target graphic, and determine a coordinate distance according to the first offset coordinate and the first graphic coordinate; The coordinate distance and the target radius are compared to obtain a comparison result, and the second offset coordinate is determined as the target offset coordinate according to the comparison result.
9. A device for acquiring a region of interest of a medical image, characterized in that: include: An image sectioning module is configured to acquire a medical image and perform sectioning processing on the medical image to obtain a two-dimensional image; a coordinate conversion module, configured to obtain first vertex coordinates of a target graphic in the first coordinate system, and perform coordinate conversion processing on the first vertex coordinates to obtain second vertex coordinates in a second coordinate system, wherein the target graphic is used to determine a region of interest of the medical image in the two-dimensional image; The region acquisition module is configured to determine a coordinate range according to the second vertex coordinates, and perform offset processing according to the coordinate range to obtain the region of interest.
10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.
11. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 8.
Citation Information
Cited By
Medical image labeling result correction method and device, electronic equipment and medium
CN119887629A
